From 4e067ceabd705201a16b4c92cf4b23f3b990326c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Sun, 13 Jul 2014 10:15:40 +0200 Subject: updated specific configuration for parsing --- inc/3rdparty/site_config/standard/forbes.com.txt | 43 +++++++++++++++--------- 1 file changed, 27 insertions(+), 16 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/forbes.com.txt (limited to 'inc/3rdparty/site_config/standard/forbes.com.txt') diff --git a/inc/3rdparty/site_config/standard/forbes.com.txt b/inc/3rdparty/site_config/standard/forbes.com.txt old mode 100644 new mode 100755 index 2381b56a..9e1d04c1 --- a/inc/3rdparty/site_config/standard/forbes.com.txt +++ b/inc/3rdparty/site_config/standard/forbes.com.txt @@ -1,16 +1,27 @@ -title: //hgroup//h1 -title: //span[@class='mainarttitle'] - -body: //div[@id='leftRail']//div[contains(@class, 'body')] - -author: //meta[@name="author"]/@content -author: //span[@class='mainartauthor'] - -date: substring-before(//hgroup//h6, '@') -date: //span[@class='mainartdate'] - -prune: no - -single_page_link: //a[contains(@href, '/print/')] - -test_url: http://www.forbes.com/forbes/2011/0509/technology-frog-design-jan-chipchase-ethnographer-birth-cool_print.html \ No newline at end of file +title: //hgroup//h1 +title: //span[@class='mainarttitle'] + +body: //div[@id='leftRail']//div[contains(@class, 'body')] + +author: //meta[@name="author"]/@content +author: //span[@class='mainartauthor'] + +date: substring-before(//hgroup//h6, '@') +date: //span[@class='mainartdate'] + +prune: no +strip: //aside +strip_id_or_class: sticky_sharing +strip_id_or_class: pagination +strip_id_or_class: controlsbox +strip_id_or_class: storyboxes +strip_id_or_class: sponsoredlinks +strip_id_or_class: nextpage +strip_id_or_class: contextuallinks +strip_id_or_class: article_actions +strip_id_or_class: engagement_block + +single_page_link: //a[contains(@href, '/print/')] + +test_url: http://www.forbes.com/forbes/2011/0509/technology-frog-design-jan-chipchase-ethnographer-birth-cool_print.html +test_url: http://www.forbes.com/sites/bruceupbin/2012/09/11/the-iphone-5-winners-and-losers/ \ No newline at end of file -- cgit v1.2.3